This article is part of the supplement: Genetic Analysis Workshop 14: Microsatellite and single-nucleotide polymorphism
A new Bayesian approach incorporating covariate information for heterogeneity and its comparison with HLOD
1 Department of Biostatistics, The University of North Texas Health Sciences Center, Fort Worth, TX 76107-2699, USA
2 Department of Statistics, The Ohio State University, Columbus, OH 43210, USA
3 Department of Biostatistics and Applied Mathematics, The University of Texas-M. D. Anderson Cancer Center, Houston, TX 77030, USA
BMC Genetics 2005, 6(Suppl 1):S138 doi:10.1186/1471-2156-6-S1-S138Published: 30 December 2005
We consider a new Bayesian approach for heterogeneity that can take into account categorical covariates, if available. We use the Genetic Analysis Workshop 14 simulated data to first compare the Bayesian approach with the heterogeneity LOD, when no covariate information is used. We find that the former is more powerful, while the two approaches have comparable false-positive rates. We then include informative covariates in the Bayesian approach and find that it tends to give more precise interval estimates of the disease gene location than when covariates are not included. We had knowledge of the simulation models at the time we performed the analyses.